US8144839B2 - Communication method and system for determining a sequence of services linked to a conversation - Google Patents

Communication method and system for determining a sequence of services linked to a conversation Download PDF

Info

Publication number
US8144839B2
US8144839B2 US12/556,319 US55631909A US8144839B2 US 8144839 B2 US8144839 B2 US 8144839B2 US 55631909 A US55631909 A US 55631909A US 8144839 B2 US8144839 B2 US 8144839B2
Authority
US
United States
Prior art keywords
conversation
services
communication system
sequence
expressions
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US12/556,319
Other versions
US20100086110A1 (en
Inventor
Mathieu Boussard
Alain Pastor
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alcatel Lucent SAS
Original Assignee
Alcatel Lucent SAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alcatel Lucent SAS filed Critical Alcatel Lucent SAS
Assigned to ALCATEL LUCENT reassignment ALCATEL LUCENT ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: BOUSSARD, MATHIEU, PASTOR, ALAIN
Publication of US20100086110A1 publication Critical patent/US20100086110A1/en
Application granted granted Critical
Publication of US8144839B2 publication Critical patent/US8144839B2/en
Assigned to CREDIT SUISSE AG reassignment CREDIT SUISSE AG SECURITY AGREEMENT Assignors: ALCATEL LUCENT
Assigned to ALCATEL LUCENT reassignment ALCATEL LUCENT RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: CREDIT SUISSE AG
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G06Q50/40
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/04Real-time or near real-time messaging, e.g. instant messaging [IM]
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/18Speech classification or search using natural language modelling
    • G10L15/1815Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Definitions

  • the present invention relates to the management of information exchanged during a conversation, in particular to a method and a system of communication for determining a sequence of services linked to a conversation in which a user takes part from a communication system.
  • the correspondents may assign tasks during the conversation relating to the organisation of the excursion.
  • One of the correspondents may therefore be responsible, following the conversation, for consulting the weather forecasts for the site, searching for a route to get to the site, reserving train tickets or contacting a third party to ask them whether they are interested in such an excursion.
  • the correspondents activate services using computer applications, such as their Web browser, installed in their communication system.
  • the correspondent responsible for finding out about the weather can open the Web browser installed on their communication system and enter a URL (Uniform Resource Locator) corresponding to a weather forecasting website. Furthermore, if this correspondent also has to reserve transport tickets, they can enter a new URL in the Web browser corresponding to a website for reserving tickets online. Likewise, if the correspondent has offered or has been asked during the conversation to send an e-mail to a friend to invite them to join the excursion, they can activate an electronic mail service available from their communication system in order to be able to send an e-mail.
  • URL Uniform Resource Locator
  • the correspondent must not forget the tasks they have been assigned during the conversation.
  • the correspondent does not yet know or is not yet thinking about running the services available from their communication system, allowing them to carry out their tasks assigned during the conversation.
  • the correspondent has determined the adapted services, in order to launch them, they must open a specific application from their communication system and manually enter information which has already been mentioned during the conversation. This operation is all the more tiresome as it has to be carried out for each time a correspondent requires a new service to carry out a task.
  • the current invention aims to facilitate the execution of the tasks a user has been assigned during a conversation.
  • a first objective of the invention concerns a method for determining a sequence of services linked to a conversation in which a user takes part from a communication system, characterised in that it includes, once the conversation is completed, the following stages:
  • a second objective of the invention concerns a communication system comprising means of allowing a user to hold a conversation, characterised in that it also comprises:
  • FIG. 1 shows in diagram form a preferred architecture of different elements making up a communication system, as well as their interactions with a view to the determination of a sequence of services according to the invention.
  • FIG. 2 represents in diagram form different interactions between a user, a messaging client and a natural-language analysis server of a communication system according to a preferred mode of the invention.
  • FIG. 3 represents a graphic interface of an instant messaging client on which a sequence of services is displayed in accordance with the invention.
  • the communication system 1 traditionally comprises a set of terminals 10 , 11 such as a telephone 10 or a computer 11 connected to a screen and from which a user 12 can hold a conversation on the telephone or via an instant messaging client.
  • a set of terminals 10 , 11 such as a telephone 10 or a computer 11 connected to a screen and from which a user 12 can hold a conversation on the telephone or via an instant messaging client.
  • Such a communication system 1 can also serve as an access point to services. Therefore, for example, when a Web browser is installed on the computer 11 , a user 12 of the communication system 1 can, among other things, access weather forecast services, consult bank accounts or reserve transport tickets from this computer 11 , with such services being available on Internet sites accessed from the Web browser.
  • an Outlook® type messaging client is installed on the communication system 1 , the user 12 may access a messaging service and therefore receive or send electronic messages from or to other users.
  • the possibility may also be envisaged of launching and then running a telephone conference service from one of the terminals 10 , 11 of the communication system 1 .
  • a user 12 when a user 12 has held a conversation, it is possible, at the end of the conversation, to retrieve and send all the expressions used during the conversation to a natural-language analysis server 13 .
  • This retrieval stage may be carried out following a voice conversation via a telephone 10 or following a qualified written conversation held via an installed instant messaging client 14 , for example on the terminal 11 of the communication system 1 .
  • the natural-language analysis server 13 then carries out a semantic analysis of the expressions retrieved and selects a plurality of services from among a list of services previously saved based on the semantic analysis carried out.
  • Each service of the list may consist of one of the aforementioned services liable to be launched and/or run from the communication system 1 .
  • the natural-language analysis server 13 carries out a contextual analysis of the expressions used during the conversation.
  • contextual analysis we refer to the analysis of an expression based on the terms used before or after said expression in the conversation, unlike the semantic analysis in which only the meaning of the expression is analysed.
  • a determination of a sequence of services selected is carried out based on the result of the contextual analysis.
  • the sequence determined is then displayed on an interface of the communication system 1 .
  • a user 12 is in conversation with at least one other user via an instant messaging software.
  • Such a conversation is initialised by the opening of a shared session from the instant messaging clients respectively installed on the communication systems of the users.
  • the conversation then involves firstly entering and successively sending expressions from the interface of their instant messaging client and secondly receiving on the interface of their client the expressions entered and sent by the other participants in the conversation.
  • the expressions entered and received are traditionally words or sentences.
  • one of the display zones 100 making up the interface of the instant messaging client is intended to display all of the expressions sent and received by the user during the conversation.
  • FIG. 3 shows a part of the graphic interface of a messaging client from which a user named Matthieu has held a conversation with a second user named Alain. All of the expressions exchanged during the conversation are displayed on the display zone 100 of the interface.
  • Matthieu can trigger a feature for scheduling tasks from his instant messaging client (stage E 1 in FIG. 2 ). All of the expressions displayed in the display zone 100 , which shows all of the expressions used during the conversation, are then sent to a natural-language analysis server 13 (stage E 2 in FIG. 2 ).
  • the server 13 then carries out a semantic analysis of the expressions which it has been sent (stage E 31 in FIG. 2 ), in order to first isolate relevant terms which can be used firstly to determine the tasks assigned to the user during the conversation and secondly to determine the services from which the user is likely to carry out these tasks.
  • the server 13 receives all of the expressions of the conversation held between the users Matthieu and Alain, the semantic analysis of the expressions “I have to phone him”, “I'll buy them online”, “I'll send you an SMS” (Short Message System) and “I'll send you a route” by the server 13 is used to determine that Matthieu (user 12 ) has to carry out four tasks after the conversation. Specifically, the user must:
  • the semantic analysis is also used to select services from which the user may carry out the tasks they have been assigned.
  • the natural-language analysis server 13 may be connected to a database 15 which we will call the service semantic reference system.
  • This reference system 15 may contain a list of services which can be launched and/or run from the communication system 1 of the user 12 .
  • Each service included in the reference system may be associated with:
  • Each leaf of the tree structure representation may correspond to a semantic term which may have an associated elementary score.
  • This elementary score represents the degree of relevance of the term of the tree structure with regard to the service with which the tree structure is associated.
  • the natural-language analysis server 13 is then adapted to carry out a comparison among the terms contained in the expressions for which the analysis was used to determine the tasks with each of the terms of the tree structures (stage E 32 in FIG. 2 ).
  • a service is selected from a comparison of the terms used in the expression and the terms of the tree structures. At the start of the comparison, each service has a score of zero. Then when a term of a structure coincides with a term of the expression, the score of the service for which the tree structure has a term coinciding with the isolated term is incremented by the elementary score associated with the term of the structure.
  • the isolated term “news” (canonical form “news”) may coincide with the term “information” of the structure through the advantageous use of an ontology describing their relation.
  • the server 13 selects the service with the highest overall score.
  • the service selected in this way is potentially the most suitable to allow the user 12 to carry out the task since it has been chosen based on an expression used in the conversation.
  • the natural-language analysis server 13 is adapted to carry out a contextual analysis of the expressions used during the conversation (stage E 33 in FIG. 2 ).
  • this analysis determines, through the expressions “to check” and “if he hasn't got them”, that the online ticket purchasing service only has to be launched if Philippe does not have the tickets.
  • the expression “afterwards” indicates that an SMS must be sent to Alain once it has been checked whether Philippe has the tickets or once Matthieu has purchased the tickets from an online purchasing service.
  • the server 13 sends the items and the meta-data associated with the selected services to the instant messaging client 14 of the user 12 (stage E 4 in FIG. 2 ).
  • the items are then displayed on the interface of the messaging client, respecting the sequence determined (stage E 5 in FIG. 2 ).
  • the display can take the form of a status diagram 101 .
  • the user 12 may, from their instant messaging client 14 , modify the sequence of services proposed or replace certain services selected by other services likely to be launched and/or run from the communication system 1 .
  • the user 12 may also trigger the launch and running of the different services. These services shall then be launched and run in sequence, respecting the order established in the sequence using the meta-data which will have been sent.
  • the result obtained by the completion of each service may be reused to launch a service for which the completion is scheduled later in the sequence.
  • a concert ticket reservation service may be run from an Internet site of a theatre, from the site of a music group or via the site of a chain of music outlets.
  • a correspondent may be contacted by telephone using a traditional telephony service or via a voice over IP type service.
  • the natural-language analysis server 13 can also be connected to a second database 16 containing user profiles.
  • a user profile can advantageously include:
  • the first telephone call service selected from the semantic analysis of the expressions used during the conversation can also be selected based on the preferences of the user 12 . For example, if the user has specified in these preferences that they only wish to hold telephone conversations using a voice over IP application, the analysis server 13 will then select a telephony service which can be run from a voice over IP application.
  • the meta-data associated with the telephony service selected may then advantageously be completed with these details. In this way, the user will not need to enter additional information to launch the telephony service from the instant messaging client 14 .
  • the analysis server may also consult the preferences of the user 12 stored previously to select a ticket reservation service specifically appreciated by the user 12 .
  • the server 13 may select the URL of a site of a music outlet stored in the favourites of the user 12 .
  • the invention is not limited to a conversation of this kind.
  • the invention may also, among other things, be applied when the conversation is a telephone conversation.
  • the communication system 1 When the conversation is a voice conversation held from a telephone terminal 10 , the communication system 1 records the conversation and sends the recording to the natural-language analysis server 13 at the end of the conversation.
  • the natural-language analysis server 13 then carries out the semantic analysis, selection of services, contextual analysis and determination of the sequence of services stages, as described previously.
  • the establishment of a telephone conversation may trigger a display application (not shown) in the communication system 1 .
  • the analysis server 13 is then adapted to send the sequence of services determined to the application which is responsible for displaying the sequence on a graphical interface of the communication system 1 .
  • the display is made, for example, on the graphical interface of the computer 11 of the communication system 1 .

Abstract

The present invention concerns a method for determining a sequence of services linked to a conversation in which a user (12) takes part from a communication system (1), as well as the associated communication system (1). According to the invention, the method includes the following stages:
    • retrieval (E2) of all the expressions used during the conversation;
    • semantic analysis (E31) of the expressions retrieved;
    • selection (E32) of a plurality of services from a list of services previously saved, based on at least said semantic analysis, with each service of said list able to be launched from said communication system (1);
    • contextual analysis (E33) of the expressions used during the conversation;
    • determination of a sequence of said services selected based on the contextual analysis;
    • display (E4) on said communication system (1) of the sequence of services selected.

Description

The present invention relates to the management of information exchanged during a conversation, in particular to a method and a system of communication for determining a sequence of services linked to a conversation in which a user takes part from a communication system.
During a telephone conversation or a conversation held via an instant messaging software (also known as a “chat”), it is common for correspondents to assign tasks relating to the subjects they are discussing.
For example, when a conversation between two correspondents concerns the preparation of an event such as an excursion to a tourist site, the correspondents may assign tasks during the conversation relating to the organisation of the excursion. One of the correspondents may therefore be responsible, following the conversation, for consulting the weather forecasts for the site, searching for a route to get to the site, reserving train tickets or contacting a third party to ask them whether they are interested in such an excursion.
Traditionally, to consult the information requested or carry out the tasks assigned during the conversation, the correspondents activate services using computer applications, such as their Web browser, installed in their communication system.
In the above example, the correspondent responsible for finding out about the weather can open the Web browser installed on their communication system and enter a URL (Uniform Resource Locator) corresponding to a weather forecasting website. Furthermore, if this correspondent also has to reserve transport tickets, they can enter a new URL in the Web browser corresponding to a website for reserving tickets online. Likewise, if the correspondent has offered or has been asked during the conversation to send an e-mail to a friend to invite them to join the excursion, they can activate an electronic mail service available from their communication system in order to be able to send an e-mail.
However, the correspondent must not forget the tasks they have been assigned during the conversation. The correspondent does not yet know or is not yet thinking about running the services available from their communication system, allowing them to carry out their tasks assigned during the conversation.
Furthermore, if the correspondent has determined the adapted services, in order to launch them, they must open a specific application from their communication system and manually enter information which has already been mentioned during the conversation. This operation is all the more tiresome as it has to be carried out for each time a correspondent requires a new service to carry out a task.
The current invention aims to facilitate the execution of the tasks a user has been assigned during a conversation.
With this in mind, a first objective of the invention concerns a method for determining a sequence of services linked to a conversation in which a user takes part from a communication system, characterised in that it includes, once the conversation is completed, the following stages:
    • retrieval of all the expressions used during the conversation;
    • semantic analysis of the expressions retrieved;
    • selection of a plurality of services from a previously saved list of services, based on at least said semantic analysis, with each service of said list able to be launched from said communication system;
    • contextual analysis of the expressions used during the conversation;
    • determination of a sequence of said services selected based on said contextual analysis;
    • display on said communication system of the sequence of services selected.
A second objective of the invention concerns a communication system comprising means of allowing a user to hold a conversation, characterised in that it also comprises:
    • a means of storage for a list of services liable to be launched from at least said communication system;
    • a natural-language analysis server able to:
      • select a plurality of services from the list of services stored, based on at least one semantic analysis of all the expressions used during the conversation;
      • determine a sequence of services selected based on a contextual analysis of all the expressions used during the conversation;
    • means of displaying the sequence of the services selected.
Other characteristics and benefits of the invention will become apparent upon reading the following description, with reference to the attached drawings, in which:
FIG. 1 shows in diagram form a preferred architecture of different elements making up a communication system, as well as their interactions with a view to the determination of a sequence of services according to the invention.
FIG. 2 represents in diagram form different interactions between a user, a messaging client and a natural-language analysis server of a communication system according to a preferred mode of the invention.
FIG. 3 represents a graphic interface of an instant messaging client on which a sequence of services is displayed in accordance with the invention.
The communication system 1, as shown in FIG. 1, traditionally comprises a set of terminals 10, 11 such as a telephone 10 or a computer 11 connected to a screen and from which a user 12 can hold a conversation on the telephone or via an instant messaging client.
Such a communication system 1 can also serve as an access point to services. Therefore, for example, when a Web browser is installed on the computer 11, a user 12 of the communication system 1 can, among other things, access weather forecast services, consult bank accounts or reserve transport tickets from this computer 11, with such services being available on Internet sites accessed from the Web browser.
Likewise, if an Outlook® type messaging client is installed on the communication system 1, the user 12 may access a messaging service and therefore receive or send electronic messages from or to other users.
The possibility may also be envisaged of launching and then running a telephone conference service from one of the terminals 10, 11 of the communication system 1.
In accordance with the method of the invention, when a user 12 has held a conversation, it is possible, at the end of the conversation, to retrieve and send all the expressions used during the conversation to a natural-language analysis server 13. This retrieval stage may be carried out following a voice conversation via a telephone 10 or following a qualified written conversation held via an installed instant messaging client 14, for example on the terminal 11 of the communication system 1.
The natural-language analysis server 13 then carries out a semantic analysis of the expressions retrieved and selects a plurality of services from among a list of services previously saved based on the semantic analysis carried out. Each service of the list may consist of one of the aforementioned services liable to be launched and/or run from the communication system 1.
Once the services are selected, the natural-language analysis server 13 carries out a contextual analysis of the expressions used during the conversation. By contextual analysis we refer to the analysis of an expression based on the terms used before or after said expression in the conversation, unlike the semantic analysis in which only the meaning of the expression is analysed.
Following this contextual analysis, a determination of a sequence of services selected is carried out based on the result of the contextual analysis. The sequence determined is then displayed on an interface of the communication system 1.
In reference to FIGS. 2 and 3, the different features of the communication system and the different stages implemented to determine a sequence of services linked to a conversation having been held will be detailed in the event that the conversation is held from an instant messaging software.
As shown in FIGS. 2 and 3, a user 12 is in conversation with at least one other user via an instant messaging software. Such a conversation is initialised by the opening of a shared session from the instant messaging clients respectively installed on the communication systems of the users.
For a user, the conversation then involves firstly entering and successively sending expressions from the interface of their instant messaging client and secondly receiving on the interface of their client the expressions entered and sent by the other participants in the conversation. The expressions entered and received are traditionally words or sentences. Traditionally, one of the display zones 100 making up the interface of the instant messaging client is intended to display all of the expressions sent and received by the user during the conversation.
FIG. 3 shows a part of the graphic interface of a messaging client from which a user named Matthieu has held a conversation with a second user named Alain. All of the expressions exchanged during the conversation are displayed on the display zone 100 of the interface.
In accordance with the method of the invention, at the end of the conversation Matthieu can trigger a feature for scheduling tasks from his instant messaging client (stage E1 in FIG. 2). All of the expressions displayed in the display zone 100, which shows all of the expressions used during the conversation, are then sent to a natural-language analysis server 13 (stage E2 in FIG. 2).
More specifically, the server 13 then carries out a semantic analysis of the expressions which it has been sent (stage E31 in FIG. 2), in order to first isolate relevant terms which can be used firstly to determine the tasks assigned to the user during the conversation and secondly to determine the services from which the user is likely to carry out these tasks.
For example, if the server 13 receives all of the expressions of the conversation held between the users Matthieu and Alain, the semantic analysis of the expressions “I have to phone him”, “I'll buy them online”, “I'll send you an SMS” (Short Message System) and “I'll send you a route” by the server 13 is used to determine that Matthieu (user 12) has to carry out four tasks after the conversation. Specifically, the user must:
    • make a telephone call;
    • make a purchase online;
    • send an SMS;
    • send a route;
The semantic analysis is also used to select services from which the user may carry out the tasks they have been assigned. To do this, the natural-language analysis server 13 may be connected to a database 15 which we will call the service semantic reference system. This reference system 15 may contain a list of services which can be launched and/or run from the communication system 1 of the user 12. Each service included in the reference system may be associated with:
    • a tree structure representation for which each leaf corresponds to a term;
    • an item (button, hyperlink, tab or any other graphical element which can be displayed on the interface of the instant messaging client) intended to be displayed on the interface of the instant messaging client if the service with which it is associated is selected;
    • meta-data comprising a set of parameters required to launch the service from the communication system 1.
Each leaf of the tree structure representation may correspond to a semantic term which may have an associated elementary score. This elementary score represents the degree of relevance of the term of the tree structure with regard to the service with which the tree structure is associated. Such a representation allows an ontological analysis.
Once the tasks which the user must carry out have been determined, the natural-language analysis server 13 is then adapted to carry out a comparison among the terms contained in the expressions for which the analysis was used to determine the tasks with each of the terms of the tree structures (stage E32 in FIG. 2).
More specifically, for each expression used to determine a task, a service is selected from a comparison of the terms used in the expression and the terms of the tree structures. At the start of the comparison, each service has a score of zero. Then when a term of a structure coincides with a term of the expression, the score of the service for which the tree structure has a term coinciding with the isolated term is incremented by the elementary score associated with the term of the structure.
Thanks to the use of an ontology allowing the link to be made between an isolated term and at least one of the terms of the structure, it is not necessary for the isolated term and the term of the structure to be totally similar for there to be a correspondence. In fact, for example, the isolated term “news” (canonical form “news”) may coincide with the term “information” of the structure through the advantageous use of an ontology describing their relation.
In this way, for each expression from which a task to be carried out has been determined, the server 13 selects the service with the highest overall score. The service selected in this way is potentially the most suitable to allow the user 12 to carry out the task since it has been chosen based on an expression used in the conversation.
In our example, four services have been selected respectively to allow Matthieu to carry out the tasks for which he is responsible. As shown in FIG. 3, the different services are:
    • “telephony service”;
    • “SMS sending service”;
    • “online ticket reservation service”;
    • “online route finding service”.
    • The telephony and SMS sending services can be carried out from applications available on the communication system 1. The ticket reservation and route finding services can be carried out from Internet sites accessible from the communication system 1.
Once the tasks are determined and the associated services are selected, it is also of interest to determine a suitable sequence in which the user 12 must carry out the tasks and launch the services knowing that the result associated with certain services may determine the running of other services.
To do this, the natural-language analysis server 13 is adapted to carry out a contextual analysis of the expressions used during the conversation (stage E33 in FIG. 2). In our example, this analysis determines, through the expressions “to check” and “if he hasn't got them”, that the online ticket purchasing service only has to be launched if Philippe does not have the tickets. Likewise, the expression “afterwards” indicates that an SMS must be sent to Alain once it has been checked whether Philippe has the tickets or once Matthieu has purchased the tickets from an online purchasing service.
Once the sequence of the services is determined, the server 13 sends the items and the meta-data associated with the selected services to the instant messaging client 14 of the user 12 (stage E4 in FIG. 2). The items are then displayed on the interface of the messaging client, respecting the sequence determined (stage E5 in FIG. 2). The display can take the form of a status diagram 101.
Advantageously, the user 12 may, from their instant messaging client 14, modify the sequence of services proposed or replace certain services selected by other services likely to be launched and/or run from the communication system 1.
Advantageously, the user 12 may also trigger the launch and running of the different services. These services shall then be launched and run in sequence, respecting the order established in the sequence using the meta-data which will have been sent.
The result obtained by the completion of each service may be reused to launch a service for which the completion is scheduled later in the sequence.
In the mode described so far, the selection of a service was carried out only based on the expressions used during the conversation. However, among the list of services present in the reference system 15, several services may be carried out using close or equivalent Internet sites or using different applications available on the communication system 1 of the user 12.
For example, a concert ticket reservation service may be run from an Internet site of a theatre, from the site of a music group or via the site of a chain of music outlets. Likewise, a correspondent may be contacted by telephone using a traditional telephony service or via a voice over IP type service.
It may therefore be of interest to refine the selection based on the previously-saved preferences of the user 12.
To do this, the natural-language analysis server 13 can also be connected to a second database 16 containing user profiles. A user profile can advantageously include:
    • a list of favourite Internet sites or pages from which the user 12 wishes to preferably consult information or carry out an action;
    • a list of user contacts containing for each contact, among other things, the surname, first name and the different applications through which the contact can be reached (electronic mail, instant messaging, traditional telephony, telephony over IP, telephone conference, etc.) as well as the different information required to enter into communication with these contacts via the applications mentioned above;
In the conversation example shown in FIG. 3, the first telephone call service selected from the semantic analysis of the expressions used during the conversation can also be selected based on the preferences of the user 12. For example, if the user has specified in these preferences that they only wish to hold telephone conversations using a voice over IP application, the analysis server 13 will then select a telephony service which can be run from a voice over IP application.
Furthermore, if the telephone contact details for Philippe are contained in the user preferences, the meta-data associated with the telephony service selected may then advantageously be completed with these details. In this way, the user will not need to enter additional information to launch the telephony service from the instant messaging client 14.
Likewise, the analysis server may also consult the preferences of the user 12 stored previously to select a ticket reservation service specifically appreciated by the user 12. For example, the server 13 may select the URL of a site of a music outlet stored in the favourites of the user 12.
The use of a database 16 containing preferences of the user therefore allows customisation of the services offered to the user 12.
Although the different characteristics and advantages of the invention have been described in reference to a conversation held from instant messaging clients, the invention is not limited to a conversation of this kind. The invention may also, among other things, be applied when the conversation is a telephone conversation.
When the conversation is a voice conversation held from a telephone terminal 10, the communication system 1 records the conversation and sends the recording to the natural-language analysis server 13 at the end of the conversation. The natural-language analysis server 13 then carries out the semantic analysis, selection of services, contextual analysis and determination of the sequence of services stages, as described previously.
Furthermore, the establishment of a telephone conversation may trigger a display application (not shown) in the communication system 1. The analysis server 13 is then adapted to send the sequence of services determined to the application which is responsible for displaying the sequence on a graphical interface of the communication system 1. The display is made, for example, on the graphical interface of the computer 11 of the communication system 1.

Claims (8)

1. Method for determining a sequence of services linked to a conversation in which a user takes part from a communication system, wherein it includes, once the conversation is completed, the following stages:
retrieval of all expression used during the conversation;
semantic analysis of expressions retrieved;
selection of a plurality of services from a list of services previously saved, based on at least said semantic analysis, with each service of said list able to be launched from said communication system;
contextual analysis of the expressions used during the conversation;
determination of a sequence of said services selected based on the contextual analysis;
display on said communication system of the sequence of services selected.
2. Method according to claim 1, wherein the selection of a plurality of services also depends on at least one previously-saved preference of said user.
3. Method according to claim 1, wherein it also comprises a sequential stage for the running of said services selected based on the determined sequence.
4. Method according to claim 1, wherein, with the conversation being a telephone conversation and the expressions being used vocally, the expression retrieval stage comprises:
the retrieval of a voice recording of the conversation;
the transmission of the voice recording to a natural-language analysis server 13.
5. Method according to claim 1, wherein, with the conversation being held from at least one instant messaging client integrated into said communication system and with the conversation consisting of expressions entered and sent from, or received by respectively, said messaging client, the retrieval stage comprises the transmission, by said instant messaging client, of all the expressions entered or received which make up the conversation to a natural-language analysis server.
6. Method according to claim 5, wherein the sequence of services selected is displayed on the interface of said instant messaging client.
7. Communication system comprising means to allow a user to hold a conversation, wherein it also comprises:
a means of storage for a list of services which can be launched from at least said communication system;
a natural-language analysis server able to:
select a plurality of services from the list of services stored, based on at least one semantic analysis of all expressions used during the conversation;
determine a sequence of services selected based on a contextual analysis of all the expressions used during the conversation;
means of displaying the sequence of the services selected.
8. Communication system according to claim 7, wherein it comprises a second storage means for storing preferences of said user, and in that said natural-language analysis server is also able to select said plurality of services depending on the preferences stored in the second storage means.
US12/556,319 2008-09-11 2009-09-09 Communication method and system for determining a sequence of services linked to a conversation Active 2030-09-07 US8144839B2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR0856129 2008-09-11
FR0856129A FR2935855B1 (en) 2008-09-11 2008-09-11 METHOD AND COMMUNICATION SYSTEM FOR DETERMINING A SERVICE SEQUENCE RELATED TO A CONVERSATION.

Publications (2)

Publication Number Publication Date
US20100086110A1 US20100086110A1 (en) 2010-04-08
US8144839B2 true US8144839B2 (en) 2012-03-27

Family

ID=40470060

Family Applications (1)

Application Number Title Priority Date Filing Date
US12/556,319 Active 2030-09-07 US8144839B2 (en) 2008-09-11 2009-09-09 Communication method and system for determining a sequence of services linked to a conversation

Country Status (7)

Country Link
US (1) US8144839B2 (en)
EP (1) EP2164212B1 (en)
JP (1) JP5242794B2 (en)
KR (1) KR20110066173A (en)
CN (1) CN101674494B (en)
FR (1) FR2935855B1 (en)
WO (1) WO2010029244A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11461152B2 (en) 2017-11-30 2022-10-04 Huawei Technologies Co., Ltd. Information input method and terminal

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101542136B1 (en) 2009-03-31 2015-08-05 삼성전자 주식회사 Method for inputting character message and mobile terminal using the same
US8612867B2 (en) * 2010-11-15 2013-12-17 Intellectual Business Machines Corporation Embedding tools in a collaboration window
KR20140011073A (en) * 2012-07-17 2014-01-28 삼성전자주식회사 Method and apparatus for recommending text
US9606977B2 (en) 2014-01-22 2017-03-28 Google Inc. Identifying tasks in messages
CN111490927B (en) * 2014-11-04 2021-07-16 华为技术有限公司 Method, device and equipment for displaying message
US11671383B2 (en) * 2016-09-26 2023-06-06 Microsoft Technology Licensing, Llc Natural language service interaction through an inbox
FR3059861A1 (en) * 2016-12-02 2018-06-08 Orange METHOD FOR PROVIDING CONTEXTUAL CONTENT DURING CONVERSATION, AND EQUIPMENT FOR IMPLEMENTING THE METHOD
US10977319B2 (en) * 2017-07-10 2021-04-13 Ebay Inc. Expandable service architecture with configurable dialogue manager
US11226832B2 (en) 2018-11-09 2022-01-18 International Business Machines Corporation Dynamic generation of user interfaces based on dialogue
CN110046238B (en) * 2019-03-29 2024-03-26 华为技术有限公司 Dialogue interaction method, graphic user interface, terminal equipment and network equipment
US10771589B1 (en) 2019-04-30 2020-09-08 Slack Technologies, Inc. Systems and methods for initiating processing actions utilizing automatically generated data of a group-based communication system

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030048880A1 (en) * 2001-09-12 2003-03-13 Mitel Knowledge Corporation Voice identification pre-screening and redirection system
WO2004029831A2 (en) 2002-09-27 2004-04-08 International Business Machines Corporation System and method for enhancing live speech with information accessed from the world wide web
US20050137877A1 (en) 2003-12-17 2005-06-23 General Motors Corporation Method and system for enabling a device function of a vehicle
US20050144013A1 (en) * 2003-11-20 2005-06-30 Jun Fujimoto Conversation control apparatus, conversation control method, and programs therefor
US7006973B1 (en) * 2000-01-31 2006-02-28 Intel Corporation Providing information in response to spoken requests
US7039722B1 (en) * 1999-11-12 2006-05-02 Fuisz Richard C Method and apparatus for translating web addresses and using numerically entered web addresses
WO2006102030A1 (en) 2005-03-17 2006-09-28 Intellisist, Inc. Providing message-based communications infrastructure for automated call center post-call processing
US20070071187A1 (en) * 2005-07-26 2007-03-29 Microsoft Corporation Providing contextual information automatically
US20100142406A1 (en) * 2004-02-27 2010-06-10 Goring Bryan R System and method for building component applications using metadata defined mapping between message and data domains
US20100174713A1 (en) * 2009-01-08 2010-07-08 International Business Machines Corporation Enhanced Content Web Browsing
US20100241978A1 (en) * 2009-03-23 2010-09-23 Genovese William M Dynamic generation of user interfaces and automated mapping of input data for service-oriented architecture-based system management applications
US7925506B2 (en) * 2004-10-05 2011-04-12 Inago Corporation Speech recognition accuracy via concept to keyword mapping
US20110228915A1 (en) * 2010-03-22 2011-09-22 Avaya Inc. Interactive Flowgraph for Analyzing Caller Utterances

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3525042B2 (en) * 1997-10-31 2004-05-10 日本電信電話株式会社 Electronic mail system, electronic mail transfer method, and recording medium recording electronic mail program
JPH11203295A (en) * 1998-01-08 1999-07-30 Ntt Data Corp Information providing device and its method
JP2001236367A (en) * 2000-02-24 2001-08-31 Hitachi Information & Control Systems Inc Handling system for claim regarding article and service
JP2002116983A (en) * 2000-10-02 2002-04-19 Hewlett Packard Co <Hp> Method and system for converting web contents
CN1219266C (en) * 2003-05-23 2005-09-14 郑方 Method for realizing multi-path dialogue for man-machine Chinese colloguial conversational system
JP2005352776A (en) * 2004-06-10 2005-12-22 Nippon Telegr & Teleph Corp <Ntt> Conversation information adaptive information service providing method, conversation information adaptive information service providing system, and device and program therefor
JP2007199768A (en) * 2006-01-23 2007-08-09 Fuji Xerox Co Ltd Document management apparatus, document management method, and computer program

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7039722B1 (en) * 1999-11-12 2006-05-02 Fuisz Richard C Method and apparatus for translating web addresses and using numerically entered web addresses
US7006973B1 (en) * 2000-01-31 2006-02-28 Intel Corporation Providing information in response to spoken requests
US20030048880A1 (en) * 2001-09-12 2003-03-13 Mitel Knowledge Corporation Voice identification pre-screening and redirection system
WO2004029831A2 (en) 2002-09-27 2004-04-08 International Business Machines Corporation System and method for enhancing live speech with information accessed from the world wide web
US20050144013A1 (en) * 2003-11-20 2005-06-30 Jun Fujimoto Conversation control apparatus, conversation control method, and programs therefor
US20050137877A1 (en) 2003-12-17 2005-06-23 General Motors Corporation Method and system for enabling a device function of a vehicle
US20100142406A1 (en) * 2004-02-27 2010-06-10 Goring Bryan R System and method for building component applications using metadata defined mapping between message and data domains
US7925506B2 (en) * 2004-10-05 2011-04-12 Inago Corporation Speech recognition accuracy via concept to keyword mapping
WO2006102030A1 (en) 2005-03-17 2006-09-28 Intellisist, Inc. Providing message-based communications infrastructure for automated call center post-call processing
US20070071187A1 (en) * 2005-07-26 2007-03-29 Microsoft Corporation Providing contextual information automatically
US20100174713A1 (en) * 2009-01-08 2010-07-08 International Business Machines Corporation Enhanced Content Web Browsing
US20100241978A1 (en) * 2009-03-23 2010-09-23 Genovese William M Dynamic generation of user interfaces and automated mapping of input data for service-oriented architecture-based system management applications
US20110228915A1 (en) * 2010-03-22 2011-09-22 Avaya Inc. Interactive Flowgraph for Analyzing Caller Utterances

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
French Search Report, Mar. 31, 2009.

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11461152B2 (en) 2017-11-30 2022-10-04 Huawei Technologies Co., Ltd. Information input method and terminal

Also Published As

Publication number Publication date
FR2935855B1 (en) 2010-09-17
JP2012502575A (en) 2012-01-26
FR2935855A1 (en) 2010-03-12
EP2164212B1 (en) 2017-08-23
EP2164212A1 (en) 2010-03-17
CN101674494A (en) 2010-03-17
WO2010029244A1 (en) 2010-03-18
KR20110066173A (en) 2011-06-16
US20100086110A1 (en) 2010-04-08
CN101674494B (en) 2012-07-18
JP5242794B2 (en) 2013-07-24

Similar Documents

Publication Publication Date Title
US8144839B2 (en) Communication method and system for determining a sequence of services linked to a conversation
RU2451329C2 (en) Context-sensitive searches and functionalities for instant text messaging applications
US10171659B2 (en) Customer portal of an intelligent automated agent for a contact center
AU2014233357B2 (en) Intelligent automated agent for a contact center
US8411841B2 (en) Real-time agent assistance
CN101112078B (en) Information communication terminal, information communication system, information communication method, information communication program, and recording medium on which program is recorded
US8290132B2 (en) Communications history log system
WO2013040037A1 (en) Multi-user communication system and method
US20090119264A1 (en) Method and system of accessing information
US20100049627A1 (en) Audio Communication Web Site Integration
US9094354B2 (en) Facilitating real-time communications in electronic message boards
US8341221B2 (en) Instant messenger location buddy
US20160078138A1 (en) Portal for sharing data over a network
CN105408887A (en) Reverse number look up
US20080084976A1 (en) Context-sensitive communications function
US8675855B2 (en) Call authorizatin for pay-per-call services
US20060075037A1 (en) Portal for managing communications of a client over a network
EP2164237B1 (en) Communication method and system for displaying a link to a service according to an expression spoken in the course of a conversation
EP2611082A1 (en) Method for instant communicating between instant messaging clients
KR20070018387A (en) Conversational agent service method and system using analysing conversation data
Soselisa et al. A user loyalty analysis of mobile instant messaging (mim) applications in manado
KR20070018388A (en) Method and system of providing conversational agent service using images

Legal Events

Date Code Title Description
AS Assignment

Owner name: ALCATEL LUCENT,FRANCE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BOUSSARD, MATHIEU;PASTOR, ALAIN;REEL/FRAME:023678/0558

Effective date: 20091026

Owner name: ALCATEL LUCENT, FRANCE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BOUSSARD, MATHIEU;PASTOR, ALAIN;REEL/FRAME:023678/0558

Effective date: 20091026

FEPP Fee payment procedure

Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: CREDIT SUISSE AG, NEW YORK

Free format text: SECURITY AGREEMENT;ASSIGNOR:LUCENT, ALCATEL;REEL/FRAME:029821/0001

Effective date: 20130130

Owner name: CREDIT SUISSE AG, NEW YORK

Free format text: SECURITY AGREEMENT;ASSIGNOR:ALCATEL LUCENT;REEL/FRAME:029821/0001

Effective date: 20130130

AS Assignment

Owner name: ALCATEL LUCENT, FRANCE

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:CREDIT SUISSE AG;REEL/FRAME:033868/0001

Effective date: 20140819

FPAY Fee payment

Year of fee payment: 4

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 8

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 12